METHOD AND APPARATUS FOR REDUNDANT DATA PROCESSING

    公开(公告)号:US20190188093A1

    公开(公告)日:2019-06-20

    申请号:US16324587

    申请日:2017-07-24

    IPC分类号: G06F11/16 G06F11/28 G06F17/50

    摘要: An arrangement for redundant data processing has an integrated circuit in which the functionality of a multi-core processor is implemented. Processor cores (40; 50) of the multi-core processor are each designed to execute a useful program. The results which emerge from the execution of the useful program by the different processor cores are compared by a comparison module of the arrangement. The processor cores differ from one another with respect to an address or data structure (AS1, AS2; DS1, DS2) which is used by a processor core to respectively store and read data in or from a memory area (70; 80) that is assigned to the particular processor core. In terms of hardware, the individual processor cores are at least partially implemented separately in the integrated circuit.

    USE OF MULTICORE PROCESSOR TO MITIGATE COMMON MODE COMPUTING FAULTS

    公开(公告)号:US20190079826A1

    公开(公告)日:2019-03-14

    申请号:US15704661

    申请日:2017-09-14

    IPC分类号: G06F11/07

    摘要: A control system includes a computing channel and an object control channel. The computing channel includes command and monitor lanes. The command lane has a first processor core with a first core architecture receiving input data and generating first data based on the input data. The monitor lane has a second processor core with second core architecture receiving the input data and generating second data based on the input data. The first core architecture and the second core architecture are dissimilar and implemented in a single system-on chip device. The computing channel outputs the first data as command data responsive to determining the first data is matched to the second data. The object control channel corresponds to the computing channel and includes an object control system receiving the command data and generating an object control signal based on the command data to control operation of at least one part of an object system.

    MAINTAINING SYSTEM RELIABILITY IN A CPU WITH CO-PROCESSORS

    公开(公告)号:US20180267868A1

    公开(公告)日:2018-09-20

    申请号:US15832251

    申请日:2017-12-05

    IPC分类号: G06F11/16

    摘要: A computer-implemented method is provided that is performed in a computer having a processor and multiple co-processors. The method includes launching a same set of operations in each of an original co-processor and a redundant co-processor, from among the multiple co-processors, to obtain respective execution signatures from the original co-processor and the redundant co-processor. The method further includes detecting an error in an execution of the set of operations by the original co-processor, by comparing the respective execution signatures. The method also includes designating the execution of the set of operations by the original co-processor as error-free and committing a result of the execution, responsive to identifying a match between the respective execution signatures. The method additionally includes performing an error recovery operation that replays the set of operations by the original co-processor and the redundant co-processor, responsive to identifying a mismatch between the respective execution signatures.

    TARGETED RECOVERY PROCESS
    6.
    发明申请

    公开(公告)号:US20180267866A1

    公开(公告)日:2018-09-20

    申请号:US15463066

    申请日:2017-03-20

    申请人: ARM Limited

    IPC分类号: G06F11/16 G06F11/18

    摘要: An apparatus comprises at least three processing circuits to perform redundant processing of common program instructions. Error detection circuitry coupled to a plurality of signal nodes of each of said at least three processing circuits comprises comparison circuitry to detect a mismatch between signals on corresponding signal nodes in said at least three processing circuits, the plurality of signal nodes forming a first group of signal nodes and a second group of signal nodes. In response to the mismatch being detected in relation to corresponding signal nodes within the first group, the error detection circuitry is configured to generate a first trigger for a full recovery process for resolving an error detected for an erroneous processing circuit using state information derived from at least two other processing circuits. In response to the mismatch being detected in relation to corresponding signal nodes within the second group the error detection circuitry is configured to generate a second trigger for a targeted recovery process for a subset of components of the erroneous processing circuit. By implementing a targeted recovery process for a subset of components of an erroneous processing circuit a cheaper recovery process may be provided.